HAR 2009: Privacy & Stylometry 3/5

Clip 3
Speaker: Mike Brennan

Privacy & Stylometry: Practical Attacks Against Authorship Attribution Techniques
Protecting your identity through your writing style: how can attacking stylometry improve privacy?

The use of statistical AI techniques in authorship recognition (or stylometry) has contributed to literary and historical breakthroughs. These successes have led to the use of these techniques in criminal investigations and prosecutions. However, few have studied adversarial attacks, motivated by a desire to protect anonymity and privacy in a variety of scenarios, and their devastating effect on the robustness of existing classification methods. Our research demonstrates how various types of attacks can reduce the effectiveness of stylometric techniques down to the level of random guessing and worse. These results are made more significant by the fact that the experimental subjects were unfamiliar with stylometric techniques, without specialized knowledge in linguistics, and spent little time on the attacks. Current work based on these results that looks deeper into implications of stylometry on privacy and anonymity on the Internet is also discussed.

For more information go to: https://har2009.org/program/events/133.en.html

Category:

Science & Technology

Tags:

• HAR
• 2009:
• Privacy
• Stylometry
• clip3